Automatic Bandwidth Estimation Strategy for High-Quality Non-Parametric Modeling based Moving Object Detection

Here, a novel and efficient moving object detection strategy by non-parametric modeling is presented. Whereas the foreground is modeled by combining color and spatial information, the background model is constructed exclusively with color information, thus resulting in a great reduction of the computational and memory requirements. The estimation of the background and foreground covariance matrices, allows us to obtain compact moving regions while the number of false detections is reduced. Additionally, the application of a tracking strategy provides a priori knowledge about the spatial position of the moving objects, which improves the performance of the Bayesian classifier

Versatile Bayesian classifier for moving object detection by non-parametric background-foreground modeling

Along the recent years, several moving object detection strategies by non-parametric background-foreground modeling have been proposed. To combine both models and to obtain the probability of a pixel to belong to the foreground, these strategies make use of Bayesian classifiers. However, these classifiers do not allow to take advantage of additional prior information at different pixels. So, we propose a novel and efficient alternative Bayesian classifier that is suitable for this kind of strategies and that allows the use of whatever prior information. Additionally, we present an effective method to dynamically estimate prior probability from the result of a particle filter-based tracking strategy.

Piezoelectric sensing and non-parametric statistical signal processing for health monitoring of hysteretic dampers used in seismic-resistant structures

The paper proposes a new application of non-parametric statistical processing of signals recorded from vibration tests for damage detection and evaluation on I-section steel segments. The steel segments investigated constitute the energy dissipating part of a new type of hysteretic damper that is used for passive control of buildings and civil engineering structures subjected to earthquake-type dynamic loadings. Two I-section steel segments with different levels of damage were instrumented with piezoceramic sensors and subjected to controlled white noise random vibrations. The signals recorded during the tests were processed using two non-parametric methods (the power spectral density method and the frequency response function method) that had never previously been applied to hysteretic dampers. The appropriateness of these methods for quantifying the level of damage on the I-shape steel segments is validated experimentally. Based on the results of the random vibrations, the paper proposes a new index that predicts the level of damage and the proximity of failure of the hysteretic damper

Regularization for sparsity in statistical analysis and machine learning

Pragmatism is the leading motivation of regularization. We can understand regularization as a modification of the maximum-likelihood estimator so that a reasonable answer could be given in an unstable or ill-posed situation. To mention some typical examples, this happens when fitting parametric or non-parametric models with more parameters than data or when estimating large covariance matrices. Regularization is usually used, in addition, to improve the bias-variance tradeoff of an estimation. Then, the definition of regularization is quite general, and, although the introduction of a penalty is probably the most popular type, it is just one out of multiple forms of regularization. In this dissertation, we focus on the applications of regularization for obtaining sparse or parsimonious representations, where only a subset of the inputs is used. A particular form of regularization, L1-regularization, plays a key role for reaching sparsity. Most of the contributions presented here revolve around L1-regularization, although other forms of regularization are explored (also pursuing sparsity in some sense). In addition to present a compact review of L1-regularization and its applications in statistical and machine learning, we devise methodology for regression, supervised classification and structure induction of graphical models. Within the regression paradigm, we focus on kernel smoothing learning, proposing techniques for kernel design that are suitable for high dimensional settings and sparse regression functions. We also present an application of regularized regression techniques for modeling the response of biological neurons. Supervised classification advances deal, on the one hand, with the application of regularization for obtaining a na¨ıve Bayes classifier and, on the other hand, with a novel algorithm for brain-computer interface design that uses group regularization in an efficient manner. Finally, we present a heuristic for inducing structures of Gaussian Bayesian networks using L1-regularization as a filter. El pragmatismo es la principal motivación de la regularización. Podemos entender la regularización como una modificación del estimador de máxima verosimilitud, de tal manera que se pueda dar una respuesta cuando la configuración del problema es inestable. A modo de ejemplo, podemos mencionar el ajuste de modelos paramétricos o no paramétricos cuando hay más parámetros que casos en el conjunto de datos, o la estimación de grandes matrices de covarianzas. Se suele recurrir a la regularización, además, para mejorar el compromiso sesgo-varianza en una estimación. Por tanto, la definición de regularización es muy general y, aunque la introducción de una función de penalización es probablemente el método más popular, éste es sólo uno de entre varias posibilidades. En esta tesis se ha trabajado en aplicaciones de regularización para obtener representaciones dispersas, donde sólo se usa un subconjunto de las entradas. En particular, la regularización L1 juega un papel clave en la búsqueda de dicha dispersión. La mayor parte de las contribuciones presentadas en la tesis giran alrededor de la regularización L1, aunque también se exploran otras formas de regularización (que igualmente persiguen un modelo disperso). Además de presentar una revisión de la regularización L1 y sus aplicaciones en estadística y aprendizaje de máquina, se ha desarrollado metodología para regresión, clasificación supervisada y aprendizaje de estructura en modelos gráficos. Dentro de la regresión, se ha trabajado principalmente en métodos de regresión local, proponiendo técnicas de diseño del kernel que sean adecuadas a configuraciones de alta dimensionalidad y funciones de regresión dispersas. También se presenta una aplicación de las técnicas de regresión regularizada para modelar la respuesta de neuronas reales. Los avances en clasificación supervisada tratan, por una parte, con el uso de regularización para obtener un clasificador naive Bayes y, por otra parte, con el desarrollo de un algoritmo que usa regularización por grupos de una manera eficiente y que se ha aplicado al diseño de interfaces cerebromáquina. Finalmente, se presenta una heurística para inducir la estructura de redes Bayesianas Gaussianas usando regularización L1 a modo de filtro.

Robust regression applied to fractal/multifractal analysis.

Fractal and multifractal are concepts that have grown increasingly popular in recent years in the soil analysis, along with the development of fractal models. One of the common steps is to calculate the slope of a linear fit commonly using least squares method. This shouldn?t be a special problem, however, in many situations using experimental data the researcher has to select the range of scales at which is going to work neglecting the rest of points to achieve the best linearity that in this type of analysis is necessary. Robust regression is a form of regression analysis designed to circumvent some limitations of traditional parametric and non-parametric methods. In this method we don?t have to assume that the outlier point is simply an extreme observation drawn from the tail of a normal distribution not compromising the validity of the regression results. In this work we have evaluated the capacity of robust regression to select the points in the experimental data used trying to avoid subjective choices. Based on this analysis we have developed a new work methodology that implies two basic steps: ? Evaluation of the improvement of linear fitting when consecutive points are eliminated based on R pvalue. In this way we consider the implications of reducing the number of points. ? Evaluation of the significance of slope difference between fitting with the two extremes points and fitted with the available points. We compare the results applying this methodology and the common used least squares one. The data selected for these comparisons are coming from experimental soil roughness transect and simulated based on middle point displacement method adding tendencies and noise. The results are discussed indicating the advantages and disadvantages of each methodology.

Contributions to Bayesian network learning with applications to neuroscience

Neuronal morphology is a key feature in the study of brain circuits, as it is highly related to information processing and functional identification. Neuronal morphology affects the process of integration of inputs from other neurons and determines the neurons which receive the output of the neurons. Different parts of the neurons can operate semi-independently according to the spatial location of the synaptic connections. As a result, there is considerable interest in the analysis of the microanatomy of nervous cells since it constitutes an excellent tool for better understanding cortical function. However, the morphologies, molecular features and electrophysiological properties of neuronal cells are extremely variable. Except for some special cases, this variability makes it hard to find a set of features that unambiguously define a neuronal type. In addition, there are distinct types of neurons in particular regions of the brain. This morphological variability makes the analysis and modeling of neuronal morphology a challenge. Uncertainty is a key feature in many complex real-world problems. Probability theory provides a framework for modeling and reasoning with uncertainty. Probabilistic graphical models combine statistical theory and graph theory to provide a tool for managing domains with uncertainty. In particular, we focus on Bayesian networks, the most commonly used probabilistic graphical model. In this dissertation, we design new methods for learning Bayesian networks and apply them to the problem of modeling and analyzing morphological data from neurons. The morphology of a neuron can be quantified using a number of measurements, e.g., the length of the dendrites and the axon, the number of bifurcations, the direction of the dendrites and the axon, etc. These measurements can be modeled as discrete or continuous data. The continuous data can be linear (e.g., the length or the width of a dendrite) or directional (e.g., the direction of the axon). These data may follow complex probability distributions and may not fit any known parametric distribution. Modeling this kind of problems using hybrid Bayesian networks with discrete, linear and directional variables poses a number of challenges regarding learning from data, inference, etc. In this dissertation, we propose a method for modeling and simulating basal dendritic trees from pyramidal neurons using Bayesian networks to capture the interactions between the variables in the problem domain. A complete set of variables is measured from the dendrites, and a learning algorithm is applied to find the structure and estimate the parameters of the probability distributions included in the Bayesian networks. Then, a simulation algorithm is used to build the virtual dendrites by sampling values from the Bayesian networks, and a thorough evaluation is performed to show the model’s ability to generate realistic dendrites. In this first approach, the variables are discretized so that discrete Bayesian networks can be learned and simulated. Then, we address the problem of learning hybrid Bayesian networks with different kinds of variables. Mixtures of polynomials have been proposed as a way of representing probability densities in hybrid Bayesian networks. We present a method for learning mixtures of polynomials approximations of one-dimensional, multidimensional and conditional probability densities from data. The method is based on basis spline interpolation, where a density is approximated as a linear combination of basis splines. The proposed algorithms are evaluated using artificial datasets. We also use the proposed methods as a non-parametric density estimation technique in Bayesian network classifiers. Next, we address the problem of including directional data in Bayesian networks. These data have some special properties that rule out the use of classical statistics. Therefore, different distributions and statistics, such as the univariate von Mises and the multivariate von Mises–Fisher distributions, should be used to deal with this kind of information. In particular, we extend the naive Bayes classifier to the case where the conditional probability distributions of the predictive variables given the class follow either of these distributions. We consider the simple scenario, where only directional predictive variables are used, and the hybrid case, where discrete, Gaussian and directional distributions are mixed. The classifier decision functions and their decision surfaces are studied at length. Artificial examples are used to illustrate the behavior of the classifiers. The proposed classifiers are empirically evaluated over real datasets. We also study the problem of interneuron classification. An extensive group of experts is asked to classify a set of neurons according to their most prominent anatomical features. A web application is developed to retrieve the experts’ classifications. We compute agreement measures to analyze the consensus between the experts when classifying the neurons. Using Bayesian networks and clustering algorithms on the resulting data, we investigate the suitability of the anatomical terms and neuron types commonly used in the literature. Additionally, we apply supervised learning approaches to automatically classify interneurons using the values of their morphological measurements. Then, a methodology for building a model which captures the opinions of all the experts is presented. First, one Bayesian network is learned for each expert, and we propose an algorithm for clustering Bayesian networks corresponding to experts with similar behaviors. Then, a Bayesian network which represents the opinions of each group of experts is induced. Finally, a consensus Bayesian multinet which models the opinions of the whole group of experts is built. A thorough analysis of the consensus model identifies different behaviors between the experts when classifying the interneurons in the experiment. A set of characterizing morphological traits for the neuronal types can be defined by performing inference in the Bayesian multinet. These findings are used to validate the model and to gain some insights into neuron morphology. Finally, we study a classification problem where the true class label of the training instances is not known. Instead, a set of class labels is available for each instance. This is inspired by the neuron classification problem, where a group of experts is asked to individually provide a class label for each instance. We propose a novel approach for learning Bayesian networks using count vectors which represent the number of experts who selected each class label for each instance. These Bayesian networks are evaluated using artificial datasets from supervised learning problems. Resumen La morfología neuronal es una característica clave en el estudio de los circuitos cerebrales, ya que está altamente relacionada con el procesado de información y con los roles funcionales. La morfología neuronal afecta al proceso de integración de las señales de entrada y determina las neuronas que reciben las salidas de otras neuronas. Las diferentes partes de la neurona pueden operar de forma semi-independiente de acuerdo a la localización espacial de las conexiones sinápticas. Por tanto, existe un interés considerable en el análisis de la microanatomía de las células nerviosas, ya que constituye una excelente herramienta para comprender mejor el funcionamiento de la corteza cerebral. Sin embargo, las propiedades morfológicas, moleculares y electrofisiológicas de las células neuronales son extremadamente variables. Excepto en algunos casos especiales, esta variabilidad morfológica dificulta la definición de un conjunto de características que distingan claramente un tipo neuronal. Además, existen diferentes tipos de neuronas en regiones particulares del cerebro. La variabilidad neuronal hace que el análisis y el modelado de la morfología neuronal sean un importante reto científico. La incertidumbre es una propiedad clave en muchos problemas reales. La teoría de la probabilidad proporciona un marco para modelar y razonar bajo incertidumbre. Los modelos gráficos probabilísticos combinan la teoría estadística y la teoría de grafos con el objetivo de proporcionar una herramienta con la que trabajar bajo incertidumbre. En particular, nos centraremos en las redes bayesianas, el modelo más utilizado dentro de los modelos gráficos probabilísticos. En esta tesis hemos diseñado nuevos métodos para aprender redes bayesianas, inspirados por y aplicados al problema del modelado y análisis de datos morfológicos de neuronas. La morfología de una neurona puede ser cuantificada usando una serie de medidas, por ejemplo, la longitud de las dendritas y el axón, el número de bifurcaciones, la dirección de las dendritas y el axón, etc. Estas medidas pueden ser modeladas como datos continuos o discretos. A su vez, los datos continuos pueden ser lineales (por ejemplo, la longitud o la anchura de una dendrita) o direccionales (por ejemplo, la dirección del axón). Estos datos pueden llegar a seguir distribuciones de probabilidad muy complejas y pueden no ajustarse a ninguna distribución paramétrica conocida. El modelado de este tipo de problemas con redes bayesianas híbridas incluyendo variables discretas, lineales y direccionales presenta una serie de retos en relación al aprendizaje a partir de datos, la inferencia, etc. En esta tesis se propone un método para modelar y simular árboles dendríticos basales de neuronas piramidales usando redes bayesianas para capturar las interacciones entre las variables del problema. Para ello, se mide un amplio conjunto de variables de las dendritas y se aplica un algoritmo de aprendizaje con el que se aprende la estructura y se estiman los parámetros de las distribuciones de probabilidad que constituyen las redes bayesianas. Después, se usa un algoritmo de simulación para construir dendritas virtuales mediante el muestreo de valores de las redes bayesianas. Finalmente, se lleva a cabo una profunda evaluaci ón para verificar la capacidad del modelo a la hora de generar dendritas realistas. En esta primera aproximación, las variables fueron discretizadas para poder aprender y muestrear las redes bayesianas. A continuación, se aborda el problema del aprendizaje de redes bayesianas con diferentes tipos de variables. Las mixturas de polinomios constituyen un método para representar densidades de probabilidad en redes bayesianas híbridas. Presentamos un método para aprender aproximaciones de densidades unidimensionales, multidimensionales y condicionales a partir de datos utilizando mixturas de polinomios. El método se basa en interpolación con splines, que aproxima una densidad como una combinación lineal de splines. Los algoritmos propuestos se evalúan utilizando bases de datos artificiales. Además, las mixturas de polinomios son utilizadas como un método no paramétrico de estimación de densidades para clasificadores basados en redes bayesianas. Después, se estudia el problema de incluir información direccional en redes bayesianas. Este tipo de datos presenta una serie de características especiales que impiden el uso de las técnicas estadísticas clásicas. Por ello, para manejar este tipo de información se deben usar estadísticos y distribuciones de probabilidad específicos, como la distribución univariante von Mises y la distribución multivariante von Mises–Fisher. En concreto, en esta tesis extendemos el clasificador naive Bayes al caso en el que las distribuciones de probabilidad condicionada de las variables predictoras dada la clase siguen alguna de estas distribuciones. Se estudia el caso base, en el que sólo se utilizan variables direccionales, y el caso híbrido, en el que variables discretas, lineales y direccionales aparecen mezcladas. También se estudian los clasificadores desde un punto de vista teórico, derivando sus funciones de decisión y las superficies de decisión asociadas. El comportamiento de los clasificadores se ilustra utilizando bases de datos artificiales. Además, los clasificadores son evaluados empíricamente utilizando bases de datos reales. También se estudia el problema de la clasificación de interneuronas. Desarrollamos una aplicación web que permite a un grupo de expertos clasificar un conjunto de neuronas de acuerdo a sus características morfológicas más destacadas. Se utilizan medidas de concordancia para analizar el consenso entre los expertos a la hora de clasificar las neuronas. Se investiga la idoneidad de los términos anatómicos y de los tipos neuronales utilizados frecuentemente en la literatura a través del análisis de redes bayesianas y la aplicación de algoritmos de clustering. Además, se aplican técnicas de aprendizaje supervisado con el objetivo de clasificar de forma automática las interneuronas a partir de sus valores morfológicos. A continuación, se presenta una metodología para construir un modelo que captura las opiniones de todos los expertos. Primero, se genera una red bayesiana para cada experto y se propone un algoritmo para agrupar las redes bayesianas que se corresponden con expertos con comportamientos similares. Después, se induce una red bayesiana que modela la opinión de cada grupo de expertos. Por último, se construye una multired bayesiana que modela las opiniones del conjunto completo de expertos. El análisis del modelo consensuado permite identificar diferentes comportamientos entre los expertos a la hora de clasificar las neuronas. Además, permite extraer un conjunto de características morfológicas relevantes para cada uno de los tipos neuronales mediante inferencia con la multired bayesiana. Estos descubrimientos se utilizan para validar el modelo y constituyen información relevante acerca de la morfología neuronal. Por último, se estudia un problema de clasificación en el que la etiqueta de clase de los datos de entrenamiento es incierta. En cambio, disponemos de un conjunto de etiquetas para cada instancia. Este problema está inspirado en el problema de la clasificación de neuronas, en el que un grupo de expertos proporciona una etiqueta de clase para cada instancia de manera individual. Se propone un método para aprender redes bayesianas utilizando vectores de cuentas, que representan el número de expertos que seleccionan cada etiqueta de clase para cada instancia. Estas redes bayesianas se evalúan utilizando bases de datos artificiales de problemas de aprendizaje supervisado.

Optimizing panchromatic image change detection based on change index multiband image analysis

This work proposes an optimization of a semi-supervised Change Detection methodology based on a combination of Change Indices (CI) derived from an image multitemporal data set. For this purpose, SPOT 5 Panchromatic images with 2.5 m spatial resolution have been used, from which three Change Indices have been calculated. Two of them are usually known indices; however the third one has been derived considering the Kullbak-Leibler divergence. Then, these three indices have been combined forming a multiband image that has been used in as input for a Support Vector Machine (SVM) classifier where four different discriminant functions have been tested in order to differentiate between change and no_change categories. The performance of the suggested procedure has been assessed applying different quality measures, reaching in each case highly satisfactory values. These results have demonstrated that the simultaneous combination of basic change indices with others more sophisticated like the Kullback-Leibler distance, and the application of non-parametric discriminant functions like those employees in the SVM method, allows solving efficiently a change detection problem.

Efectos de una intervención nutricional personalizada a largo plazo sobre los hábitos alimentarios de jugadores profesionales de baloncesto y su influencia en la percepción del esfuerzo y la fatiga

El presente trabajo consistió en el desarrollo de una intervención nutricional a largo plazo llevada a cabo con jugadores profesionales de baloncesto, en función al cumplimiento de las recomendaciones nutricionales, con los siguientes dos objetivos: 1) valorar los cambios que dicha intervención produce sobre las prácticas nutricionales diarias de estos deportistas y 2) conocer la influencia de las modificaciones nutricionales producidas sobre la tasa de percepción del esfuerzo por sesión (RPE-Sesión) y la fatiga, a lo largo de una temporada competitiva, tanto para entrenamientos como partidos oficiales. Los objetivos del estudio se fundamentan en: 1) la numerosa evidencia científica que muestra la inadecuación de los hábitos nutricionales de los jugadores de baloncesto y otros deportistas respecto a las recomendaciones nutricionales; 2) el hecho ampliamente reconocido en la literatura especializada de que una ingesta nutricional óptima permite maximizar el rendimiento deportivo (a nivel físico y cognitivo), promoviendo una rápida recuperación y disminuyendo el riesgo de enfermedades y lesiones deportivas. No obstante, pocos estudios han llevado a cabo una intervención nutricional a largo plazo para mejorar los hábitos alimentarios de los deportistas y ninguno de ellos fue realizado con jugadores de baloncesto; 3) la elevada correlación entre la percepción del esfuerzo (RPE) y variables fisiológicas relacionadas al desarrollo de un ejercicio (por ej.: frecuencia cardíaca, consumo máximo de oxígeno o lactato sanguíneo) y los múltiples estudios que muestran la atenuación de la RPE durante la realización del ejercicio mediante una ingesta puntual de nutrientes, (especialmente de hidratos de carbono) aunque ninguno fue desarrollado en baloncesto; 4) el estudio incipiente de la relación entre la ingesta nutricional y la RPE-Sesión, siendo éste un método validado en baloncesto y otros deportes de equipo como indicador de la carga de trabajo interna, el rendimiento deportivo y la intensidad del ejercicio realizado; 5) el hecho de que la fatiga constituye uno de los principales factores influyentes en la percepción del esfuerzo y puede ser retrasada y/o atenuada mediante la ingesta de carbohidratos, pudiendo disminuir consecuentemente la RPE-Sesión y la carga interna del esfuerzo físico, potenciando el rendimiento deportivo y las adaptaciones inducidas por el entrenamiento; 6) la reducida evidencia acerca del comportamiento de la RPE-Sesión ante la modificación de la ingesta de nutrientes, encontrándose sólo un estudio llevado a cabo en baloncesto y 7) la ausencia de investigaciones acerca de la influencia que puede tener la mejora del patrón nutricional de los jugadores sobre la RPE-Sesión y la fatiga, desconociéndose si la adecuación de los hábitos nutricionales conduce a una disminución de estas variables en el largo plazo para todos los entrenamientos y partidos oficiales a nivel profesional. Por todo esto, este trabajo comienza con una introducción que presenta el marco teórico de la importancia y función de la nutrición en el deporte, así como de las recomendaciones nutricionales actuales a nivel general y para baloncesto. Además, se describen las intervenciones nutricionales llevadas a cabo previamente con otros deportistas y las consecuentes modificaciones sobre el patrón alimentario, coincidiendo este aspecto con el primer objetivo del presente estudio. Posteriormente, se analiza la RPE, la RPE-Sesión y la fatiga, focalizando el estudio en la relación de dichas variables con la carga de trabajo físico, la intensidad del entrenamiento, el rendimiento deportivo y la recuperación post ejercicio. Finalmente, se combinan todos los aspectos mencionados: ingesta nutricional, RPE percepción del esfuerzo y fatiga, con el fin de conocer la situación actual del estudio de la relación entre dichas variables, conformando la base del segundo objetivo de este estudio. Seguidamente, se exponen y fundamentan los objetivos antes mencionados, para dar lugar después a la explicación de la metodología utilizada en el presente estudio. Ésta consistió en un diseño de estudios de caso, aplicándose una intervención nutricional personalizada a tres jugadores de baloncesto profesional (cada jugador = un estudio de caso; n = 1), con el objetivo de adecuar su ingesta nutricional en el largo plazo a las recomendaciones nutricionales. A su vez, se analizó la respuesta individual de cada uno de los casos a dicha intervención para los dos objetivos del estudio. Para ello, cada jugador completó un registro diario de alimentos (7 días; pesada de alimentos) antes, durante y al final de la intervención. Además, los sujetos registraron diariamente a lo largo del estudio la RPE-Sesión y la fatiga en entrenamientos físicos y de balón y en partidos oficiales de liga, controlándose además en forma cuantitativa otras variables influyentes como el estado de ánimo y el sueño. El análisis de los datos consistió en el cálculo de los estadísticos descriptivos para todas las variables, la comparación de la ingesta en los diferentes momentos evaluados con las recomendaciones nutricionales y una comparación de medias no paramétrica entre el período pre intervención y durante la intervención con el test de Wilcoxon (medidas repetidas) para todas las variables. Finalmente, se relacionaron los cambios obtenidos en la ingesta nutricional con la percepción del esfuerzo y la fatiga y la posible influencia del estado de ánimo y el sueño, a través de un estudio correlacional (Tau_b de Kendall). Posteriormente, se presentan los resultados obtenidos y la discusión de los mismos, haciendo referencia a la evidencia científica relacionada que se encuentra publicada hasta el momento, la cual facilitó el análisis de la relación entre RPE-Sesión, fatiga y nutrición a lo largo de una temporada. Los principales hallazgos y su correspondiente análisis, por lo tanto, pueden resumirse en los siguientes: 1) los tres jugadores de baloncesto profesional presentaron inicialmente hábitos nutricionales inadecuados, haciendo evidente la necesidad de un nutricionista deportivo dentro del cuerpo técnico de los equipos profesionales; 2) las principales deficiencias correspondieron a un déficit pronunciado de energía e hidratos de carbono, que fueron reducidas con la intervención nutricional; 3) la ingesta excesiva de grasa total, ácidos grasos saturados, etanol y proteínas que se halló en alguno/s de los casos, también se adecuó a las recomendaciones después de la intervención; 4) la media obtenida durante un período de la temporada para la RPE-Sesión y la fatiga de entrenamientos, podría ser disminuida en un jugador individual mediante el incremento de su ingesta de carbohidratos a largo plazo, siempre que no existan alteraciones psico-emocionales relevantes; 5) el comportamiento de la RPE-Sesión de partidos oficiales no parece estar influido por los factores nutricionales modificados en este estudio, dependiendo más de la variación de elementos externos no controlables, intrínsecos a los partidos de baloncesto profesional. Ante estos resultados, se pudo observar que las diferentes características de los jugadores y las distintas respuestas obtenidas después de la intervención, reforzaron la importancia de utilizar un diseño de estudio de casos para el análisis de los deportistas de élite y, asimismo, de realizar un asesoramiento nutricional personalizado. Del mismo modo, la percepción del esfuerzo y la fatiga de cada jugador evolucionaron de manera diferente después de la intervención nutricional, lo cual podría depender de las diferentes características de los sujetos, a nivel físico, psico-social, emocional y contextual. Por ello, se propone que el control riguroso de las variables cualitativas que parecen influir sobre la RPE y la fatiga a largo plazo, facilitaría la comprensión de los datos y la determinación de factores desconocidos que influyen sobre estas variables. Finalmente, al ser la RPE-Sesión un indicador directo de la carga interna del entrenamiento, es decir, del estrés psico-fisiológico experimentado por el deportista, la posible atenuación de esta variable mediante la adecuación de los hábitos nutricionales, permitiría aplicar las cargas externas de entrenamiento planificadas, con menor estrés interno y mejor recuperación entre sesiones, disminuyendo también la sensación de fatiga, a pesar del avance de la temporada. ABSTRACT This study consisted in a long-term nutritional intervention carried out with professional basketball players according to nutritional recommendations, with the following two main objectives: 1) to evaluate the changes produced by the intervention on daily nutritional practices of these athletes and 2) to determine the influence of long term nutritional intake modifications on the rate of perceived exertion per session (Session-RPE) and fatigue, throughout a competitive season for training as well as competition games. These objectives are based on: 1) much scientific evidence that shows an inadequacy of the nutritional habits of basketball players and other athletes regarding nutritional recommendations; 2) the fact widely recognized in the scientific literature that an optimal nutrition allows to achieve the maximum performance of an athlete (both physically and cognitively), promoting fast recovery and decreasing risks of sports injuries and illnesses. However, only few studies carried out a long term nutritional intervention to improve nutritional practices of athletes and it could not be found any research with basketball players; 3) the high correlation between the rate of perceived exertion (RPE) and physiological variables related to the performance of physical exercise (e.g.: heart rate, maximum consumption of oxygen or blood lactate) and multiple studies showing the attenuation of RPE during exercise due to the intake of certain nutrients (especially carbohydrates), while none of them was developed in basketball; 4) correlation between nutritional intake and Session-RPE has been recently studied for the first time. Session-RPE method has been validated in basketball players and other team sports as an indicator of internal workload, sports performance and exercise intensity; 5) fatigue is considered one of the main influential factor on RPE and sport performance. It has also been observed that carbohydrates intake may delay or mitigate the onset of fatigue and, thus, decrease the perceived exertion and the internal training load, which could improve sports performance and training-induced adaptations; 6) there are few studies evaluating the influence of nutrient intake on Session-RPE and only one of them has been carried out with basketball players. Moreover, it has not been analyzed the possible effects of the adequacy of players’ nutritional habits through a nutritional intervention on Session-RPE and fatigue, variables that could be decreased for all training session and competition games because of an improvement of daily nutritional intake. Therefore, this work begins with an introduction that provides the conceptual framework of this research focused on the key role of nutrition in sport, as well as on the current nutritional recommendations for athletes and specifically for basketball players. In addition, previous nutritional interventions carried out with other athletes are described, as well as consequential modifications on their food pattern, coinciding with the first objective of the present study. Subsequently, RPE, Session-RPE and fatigue are analyzed, with focus on their correlation with physical workload, training intensity, sports performance and recovery. Finally, all the aforementioned aspects (nutritional intake, RPE and fatigue) were combined in order to know the current status of the relation between each other, this being the base for the second objective of this study. Subsequently, the objectives mentioned above are explained, continuing with the explanation of the methodology used in the study. The methodology consisted of a case-study design, carrying out a long term nutritional intervention with three professional basketball players (each player = one case study; n = 1), in order to adapt their nutritional intake to nutritional recommendations. At the same time, the individual response of each player to the intervention was analyzed for the two main objectives of the study. Each player completed a food diary (7 days; weighing food) in three moments: before, during and at the end of the intervention. In addition, the Session-RPE and fatigue were daily recorded throughout the study for all trainings (training with ball and resistance training) and competition games. At the same time, other potentially influential variables such as mood state and sleeping were daily controlled throughout the study. Data analysis consisted in descriptive statistics calculation for all the variables of the study, the comparison between nutritional intake (evaluated at different times) and nutritional recommendations and a non-parametric mean comparison between pre intervention and during intervention periods was made by Wilcoxon test (repeated measurements) for all variables too. Finally, the changes in nutritional intake, mood state and sleeping were correlated with the perceived exertion and fatigue through correctional study (Tau_b de Kendall). After the methodology, the study results and the associated discussion are presented. The discussion is based on the current scientific evidence that contributes to understand the relation between Session-RPE, fatigue and nutrition throughout the competitive season. The main findings and results analysis can be summarized as follows: 1) the three professional basketball players initially had inadequate nutritional habits and this clearly shows the need of a sports nutritionist in the coaching staff of professional teams; (2) the major deficiencies of the three players’ diet corresponded to a pronounced deficit of energy intake and carbohydrates consumption which were reduced with nutritional intervention; (3) the excessive intake of total fat, saturated fatty acids, ethanol and protein found in some cases were also adapted to the recommendations after the intervention; (4) Session-RPE mean and fatigue of a certain period of the competition season, could be decreased in an individual player by increasing his carbohydrates intake in the long term, if there are no relevant psycho-emotional disorders; (5) the behavior of the Session-RPE in competition games does not seem to be influenced by the nutritional factors modified in this study. They seem to depend much more on the variation of external non-controllable factors associated with the professional basketball games. Given these results, the different characteristics of each player and the diverse responses observed after the intervention in each individual for all the variables, reinforced the importance of the use of a case study design for research with elite athletes as well as personalized nutritional counselling. In the same way, the different responses obtained for RPE and fatigue in the long term for each player due to modification of nutritional habits, show that there is a dependence of such variables on the physical, psychosocial, emotional and contextual characteristics of each player. Therefore it is proposed that the rigorous control of the qualitative variables that seem to influence the RPE and fatigue in the long term, may facilitate the understanding of data and the determination of unknown factors that could influence these variables. Finally, because Session-RPE is a direct indicator of the internal load of training (psycho-physiological stress experienced by the athlete), the possible attenuation of Session-RPE through the improvement in nutritional habits, would allow to apply the planned external loads of training with less internal stress and better recovery between sessions, with a decrease in fatigue, despite of the advance of the season.

Spatio-temporal distribution of pyrethroids in soil in Mediterranean paddy fields

Purpose The demand of rice by the increase in population in many countries has intensified the application of pesticides and the use of poor quality water to irrigate fields. The terrestrial environment is one compartment affected by these situations, where soil is working as a reservoir, retaining organic pollutants. Therefore, it is necessary to develop methods to determine insecticides in soil and monitor susceptible areas to be contaminated, applying adequate techniques to remediate them. Materials and methods This study investigates the occurrence of ten pyrethroid insecticides (PYs) and its spatio-temporal variance in soil at two different depths collected in two periods (before plow and during rice production), in a paddy field area located in the Mediterranean coast. Pyrethroids were quantified using gas chromatography?mass spectrometry (GC?MS) after ultrasound-assisted extraction with ethyl acetate. The results obtained were assessed statistically using non-parametric methods, and significant statistical differences (p < 0.05) in pyrethroids content with soil depth and proximity to wastewater treatment plants were evaluated. Moreover, a geographic information system (GIS) was used to monitor the occurrence of PYs in paddy fields and detect risk areas. Results and discussion Pyrethroids were detected at concentrations ?57.0 ng g?1 before plow and ?62.3 ng g?1 during rice production, being resmethrin and cyfluthrin the compounds found at higher concentrations in soil. Pyrethroids were detected mainly at the top soil, and a GIS program was used to depict the obtained results, showing that effluents from wastewater treatment plants (WWTPs) were the main sources of soil contamination. No toxic effects were expected to soil organisms, but it is of concern that PYs may affect aquatic organisms, which represents the worst case scenario. Conclusions A methodology to determine pyrethroids in soil was developed to monitor a paddy field area. The use of water fromWWTPs to irrigate rice fields is one of the main pollution sources of pyrethroids. It is a matter of concern that PYs may present toxic effects on aquatic organisms, as they can be desorbed from soil. Phytoremediation may play an important role in this area, reducing the possible risk associated to PYs levels in soil.

Estimadores bayesianos de la fiabilidad con muestreo censurado

El estudio de la fiabilidad de componentes y sistemas tiene gran importancia en diversos campos de la ingenieria, y muy concretamente en el de la informatica. Al analizar la duracion de los elementos de la muestra hay que tener en cuenta los elementos que no fallan en el tiempo que dure el experimento, o bien los que fallen por causas distintas a la que es objeto de estudio. Por ello surgen nuevos tipos de muestreo que contemplan estos casos. El mas general de ellos, el muestreo censurado, es el que consideramos en nuestro trabajo. En este muestreo tanto el tiempo hasta que falla el componente como el tiempo de censura son variables aleatorias. Con la hipotesis de que ambos tiempos se distribuyen exponencialmente, el profesor Hurt estudio el comportamiento asintotico del estimador de maxima verosimilitud de la funcion de fiabilidad. En principio parece interesante utilizar metodos Bayesianos en el estudio de la fiabilidad porque incorporan al analisis la informacion a priori de la que se dispone normalmente en problemas reales. Por ello hemos considerado dos estimadores Bayesianos de la fiabilidad de una distribucion exponencial que son la media y la moda de la distribucion a posteriori. Hemos calculado la expansion asint6tica de la media, varianza y error cuadratico medio de ambos estimadores cuando la distribuci6n de censura es exponencial. Hemos obtenido tambien la distribucion asintotica de los estimadores para el caso m3s general de que la distribucion de censura sea de Weibull. Dos tipos de intervalos de confianza para muestras grandes se han propuesto para cada estimador. Los resultados se han comparado con los del estimador de maxima verosimilitud, y con los de dos estimadores no parametricos: limite producto y Bayesiano, resultando un comportamiento superior por parte de uno de nuestros estimadores. Finalmente nemos comprobado mediante simulacion que nuestros estimadores son robustos frente a la supuesta distribuci6n de censura, y que uno de los intervalos de confianza propuestos es valido con muestras pequenas. Este estudio ha servido tambien para confirmar el mejor comportamiento de uno de nuestros estimadores. SETTING OUT AND SUMMARY OF THE THESIS When we study the lifetime of components it's necessary to take into account the elements that don't fail during the experiment, or those that fail by reasons which are desirable to exclude from consideration. The model of random censorship is very usefull for analysing these data. In this model the time to failure and the time censor are random variables. We obtain two Bayes estimators of the reliability function of an exponential distribution based on randomly censored data. We have calculated the asymptotic expansion of the mean, variance and mean square error of both estimators, when the censor's distribution is exponential. We have obtained also the asymptotic distribution of the estimators for the more general case of censor's Weibull distribution. Two large-sample confidence bands have been proposed for each estimator. The results have been compared with those of the maximum likelihood estimator, and with those of two non parametric estimators: Product-limit and Bayesian. One of our estimators has the best behaviour. Finally we have shown by simulation, that our estimators are robust against the assumed censor's distribution, and that one of our intervals does well in small sample situation.

Segmentación de Secuencias de Vídeo: análisis y desarrollo de estrategias para la detección de cambios de toma y para la detección de objetos móviles

The important technological advances experienced along the last years have resulted in an important demand for new and efficient computer vision applications. On the one hand, the increasing use of video editing software has given rise to a necessity for faster and more efficient editing tools that, in a first step, perform a temporal segmentation in shots. On the other hand, the number of electronic devices with integrated cameras has grown enormously. These devices require new, fast, and efficient computer vision applications that include moving object detection strategies. In this dissertation, we propose a temporal segmentation strategy and several moving object detection strategies, which are suitable for the last generation of computer vision applications requiring both low computational cost and high quality results. First, a novel real-time high-quality shot detection strategy is proposed. While abrupt transitions are detected through a very fast pixel-based analysis, gradual transitions are obtained from an efficient edge-based analysis. Both analyses are reinforced with a motion analysis that allows to detect and discard false detections. This analysis is carried out exclusively over a reduced amount of candidate transitions, thus maintaining the computational requirements. On the other hand, a moving object detection strategy, which is based on the popular Mixture of Gaussians method, is proposed. This strategy, taking into account the recent history of each image pixel, adapts dynamically the amount of Gaussians that are required to model its variations. As a result, we improve significantly the computational efficiency with respect to other similar methods and, additionally, we reduce the influence of the used parameters in the results. Alternatively, in order to improve the quality of the results in complex scenarios containing dynamic backgrounds, we propose different non-parametric based moving object detection strategies that model both background and foreground. To obtain high quality results regardless of the characteristics of the analyzed sequence we dynamically estimate the most adequate bandwidth matrices for the kernels that are used in the background and foreground modeling. Moreover, the application of a particle filter allows to update the spatial information and provides a priori knowledge about the areas to analyze in the following images, enabling an important reduction in the computational requirements and improving the segmentation results. Additionally, we propose the use of an innovative combination of chromaticity and gradients that allows to reduce the influence of shadows and reflects in the detections.

Evaluación de la profundidad de la fisuración superficial descendente en pavimentos asfálticos mediante técnicas de ultrasonidos. Validación teórico-práctica y modelos

La fisuración iniciada en la superficie de los pavimentos asfálticos constituye uno de los más frecuentes e importantes modos de deterioro que tienen lugar en los firmes bituminosos, como han demostrado los estudios teóricos y experimentales llevados a cabo en la última década. Sin embargo, este mecanismo de fallo no ha sido considerado por los métodos tradicionales de diseño de estos firmes. El concepto de firmes de larga duración se fundamenta en un adecuado seguimiento del proceso de avance en profundidad de estos deterioros y la intervención en el momento más apropiado para conseguir mantenerlos confinados como fisuras de profundidad parcial en la capa superficial más fácilmente accesible y reparable, de manera que pueda prolongarse la durabilidad y funcionalidad del firme y reducir los costes generalizados de su ciclo de vida. Por lo tanto, para la selección de la estrategia óptima de conservación de los firmes resulta esencial disponer de metodologías que posibiliten la identificación precisa in situ de la fisuración descendente, su seguimiento y control, y que además permitan una determinación fiable y con alto rendimiento de su profundidad y extensión. En esta Tesis Doctoral se presentan los resultados obtenidos mediante la investigación sistemática de laboratorio e in situ llevada a cabo para la obtención de datos sobre fisuración descendente en firmes asfálticos y para el estudio de procedimientos de evaluación de la profundidad de este tipo de fisuras empleando técnicas de ultrasonidos. Dichos resultados han permitido comprobar que la metodología no destructiva propuesta, de rápida ejecución, bajo coste y sencilla implementación (principalmente empleada hasta el momento en estructuras metálicas y de hormigón, debido a las dificultades que introduce la naturaleza viscoelástica de los materiales bituminosos) puede ser aplicada con suficiente fiabilidad y repetibilidad sobre firmes asfálticos. Las medidas resultan asimismo independientes del espesor total del firme. Además, permite resolver algunos de los inconvenientes frecuentes que presentan otros métodos de diagnóstico de las fisuras de pavimentos, tales como la extracción de testigos (sistema destructivo, de alto coste y prolongados tiempos de interrupción del tráfico) o algunas otras técnicas no destructivas como las basadas en medidas de deflexiones o el georradar, las cuales no resultan suficientemente precisas para la investigación de fisuras superficiales. Para ello se han realizado varias campañas de ensayos sobre probetas de laboratorio en las que se han estudiado diferentes condiciones empíricas como, por ejemplo, distintos tipos de mezclas bituminosas en caliente (AC, SMA y PA), espesores de firme y adherencias entre capas, temperaturas, texturas superficiales, materiales de relleno y agua en el interior de las grietas, posición de los sensores y un amplio rango de posibles profundidades de fisura. Los métodos empleados se basan en la realización de varias medidas de velocidad o de tiempo de transmisión del pulso ultrasónico sobre una única cara o superficie accesible del material, de manera que resulte posible obtener un coeficiente de transmisión de la señal (mediciones relativas o autocompensadas). Las mediciones se han realizado a bajas frecuencias de excitación mediante dos equipos de ultrasonidos diferentes dotados, en un caso, de transductores de contacto puntual seco (DPC) y siendo en el otro instrumento de contacto plano a través de un material especialmente seleccionado para el acoplamiento (CPC). Ello ha permitido superar algunos de los tradicionales inconvenientes que presenta el uso de los transductores convencionales y no precisar preparación previa de las superficies. La técnica de autocalibración empleada elimina los errores sistemáticos y la necesidad de una calibración local previa, demostrando el potencial de esta tecnología. Los resultados experimentales han sido comparados con modelos teóricos simplificados que simulan la propagación de las ondas ultrasónicas en estos materiales bituminosos fisurados, los cuales han sido deducidos previamente mediante un planteamiento analítico y han permitido la correcta interpretación de dichos datos empíricos. Posteriormente, estos modelos se han calibrado mediante los resultados de laboratorio, proporcionándose sus expresiones matemáticas generalizadas y gráficas para su uso rutinario en las aplicaciones prácticas. Mediante los ensayos con ultrasonidos efectuados en campañas llevadas a cabo in situ, acompañados de la extracción de testigos del firme, se han podido evaluar los modelos propuestos. El máximo error relativo promedio en la estimación de la profundidad de las fisuras al aplicar dichos modelos no ha superado el 13%, con un nivel de confianza del 95%, en el conjunto de todos los ensayos realizados. La comprobación in situ de los modelos ha permitido establecer los criterios y las necesarias recomendaciones para su utilización sobre firmes en servicio. La experiencia obtenida posibilita la integración de esta metodología entre las técnicas de auscultación para la gestión de su conservación. Abstract Surface-initiated cracking of asphalt pavements constitutes one of the most frequent and important types of distress that occur in flexible bituminous pavements, as clearly has been demonstrated in the technical and experimental studies done over the past decade. However, this failure mechanism has not been taken into consideration for traditional methods of flexible pavement design. The concept of long-lasting pavements is based on adequate monitoring of the depth and extent of these deteriorations and on intervention at the most appropriate moment so as to contain them in the surface layer in the form of easily-accessible and repairable partial-depth topdown cracks, thereby prolonging the durability and serviceability of the pavement and reducing the overall cost of its life cycle. Therefore, to select the optimal maintenance strategy for perpetual pavements, it becomes essential to have access to methodologies that enable precise on-site identification, monitoring and control of top-down propagated cracks and that also permit a reliable, high-performance determination of the extent and depth of cracking. This PhD Thesis presents the results of systematic laboratory and in situ research carried out to obtain information about top-down cracking in asphalt pavements and to study methods of depth evaluation of this type of cracking using ultrasonic techniques. These results have demonstrated that the proposed non-destructive methodology –cost-effective, fast and easy-to-implement– (mainly used to date for concrete and metal structures, due to the difficulties caused by the viscoelastic nature of bituminous materials) can be applied with sufficient reliability and repeatability to asphalt pavements. Measurements are also independent of the asphalt thickness. Furthermore, it resolves some of the common inconveniences presented by other methods used to evaluate pavement cracking, such as core extraction (a destructive and expensive procedure that requires prolonged traffic interruptions) and other non-destructive techniques, such as those based on deflection measurements or ground-penetrating radar, which are not sufficiently precise to measure surface cracks. To obtain these results, extensive tests were performed on laboratory specimens. Different empirical conditions were studied, such as various types of hot bituminous mixtures (AC, SMA and PA), differing thicknesses of asphalt and adhesions between layers, varied temperatures, surface textures, filling materials and water within the crack, different sensor positions, as well as an ample range of possible crack depths. The methods employed in the study are based on a series of measurements of ultrasonic pulse velocities or transmission times over a single accessible side or surface of the material that make it possible to obtain a signal transmission coefficient (relative or auto-calibrated readings). Measurements were taken at low frequencies by two short-pulse ultrasonic devices: one equipped with dry point contact transducers (DPC) and the other with flat contact transducers that require a specially-selected coupling material (CPC). In this way, some of the traditional inconveniences presented by the use of conventional transducers were overcome and a prior preparation of the surfaces was not required. The auto-compensating technique eliminated systematic errors and the need for previous local calibration, demonstrating the potential for this technology. The experimental results have been compared with simplified theoretical models that simulate ultrasonic wave propagation in cracked bituminous materials, which had been previously deduced using an analytical approach and have permitted the correct interpretation of the aforementioned empirical results. These models were subsequently calibrated using the laboratory results, providing generalized mathematical expressions and graphics for routine use in practical applications. Through a series of on-site ultrasound test campaigns, accompanied by asphalt core extraction, it was possible to evaluate the proposed models, with differences between predicted crack depths and those measured in situ lower than 13% (with a confidence level of 95%). Thereby, the criteria and the necessary recommendations for their implementation on in-service asphalt pavements have been established. The experience obtained through this study makes it possible to integrate this methodology into the evaluation techniques for pavement management systems.

Comparative analysis of meta-analysis methods: when to use which?

Background: Several meta-analysis methods can be used to quantitatively combine the results of a group of experiments, including the weighted mean difference, statistical vote counting, the parametric response ratio and the non-parametric response ratio. The software engineering community has focused on the weighted mean difference method. However, other meta-analysis methods have distinct strengths, such as being able to be used when variances are not reported. There are as yet no guidelines to indicate which method is best for use in each case. Aim: Compile a set of rules that SE researchers can use to ascertain which aggregation method is best for use in the synthesis phase of a systematic review. Method: Monte Carlo simulation varying the number of experiments in the meta analyses, the number of subjects that they include, their variance and effect size. We empirically calculated the reliability and statistical power in each case Results: WMD is generally reliable if the variance is low, whereas its power depends on the effect size and number of subjects per meta-analysis; the reliability of RR is generally unaffected by changes in variance, but it does require more subjects than WMD to be powerful; NPRR is the most reliable method, but it is not very powerful; SVC behaves well when the effect size is moderate, but is less reliable with other effect sizes. Detailed tables of results are annexed. Conclusions: Before undertaking statistical aggregation in software engineering, it is worthwhile checking whether there is any appreciable difference in the reliability and power of the methods. If there is, software engineers should select the method that optimizes both parameters.

Moving Object Detection for Real-Time High-Quality Lightweight Applications on Smart Cameras

Here, a novel and efficient strategy for moving object detection by non-parametric modeling on smart cameras is presented. Whereas the background is modeled using only color information, the foreground model combines color and spatial information. The application of a particle filter allows the update of the spatial information and provides a priori information about the areas to analyze in the following images, enabling an important reduction in the computational requirements and improving the segmentation results

Ensemble transcript interaction networks: A case study on Alzheimer's disease

Systems biology techniques are a topic of recent interest within the neurological field. Computational intelligence (CI) addresses this holistic perspective by means of consensus or ensemble techniques ultimately capable of uncovering new and relevant findings. In this paper, we propose the application of a CI approach based on ensemble Bayesian network classifiers and multivariate feature subset selection to induce probabilistic dependences that could match or unveil biological relationships. The research focuses on the analysis of high-throughput Alzheimer's disease (AD) transcript profiling. The analysis is conducted from two perspectives. First, we compare the expression profiles of hippocampus subregion entorhinal cortex (EC) samples of AD patients and controls. Second, we use the ensemble approach to study four types of samples: EC and dentate gyrus (DG) samples from both patients and controls. Results disclose transcript interaction networks with remarkable structures and genes not directly related to AD by previous studies. The ensemble is able to identify a variety of transcripts that play key roles in other neurological pathologies. Classical statistical assessment by means of non-parametric tests confirms the relevance of the majority of the transcripts. The ensemble approach pinpoints key metabolic mechanisms that could lead to new findings in the pathogenesis and development of AD